Back
The MPI-IS community is invited to the February 11 keynote by Dr. Michael Muehlebach, the scientific highlight of the 2026 IMPRS-IS Interview Symposium, examining learning through the lens of dynamical systems and interaction.
All members of the MPI for Intelligent Systems (MPI-IS) community are invited to attend the keynote of the 2026 IMPRS-IS Interview Symposium. The symposium runs from Thursday, February 5 through Friday, February 13, 2026, and its scientific highlight will be a keynote by Dr. Michael Muehlebach (Max Planck Institute for Intelligent Systems) on Wednesday, February 11.
The International Max Planck Research School for Intelligent Systems (IMPRS-IS) brings together the Max Planck Institute for Intelligent Systems with the University of Stuttgart and the University of Tübingen to form a highly visible and unique graduate school of internationally recognized faculty working at the leading edge of the field. The program is a key element of Baden-Württemberg’s Cyber Valley initiative to accelerate basic research and commercial development in artificial intelligence.
Each year, IMPRS-IS hosts its Interview Symposium as part of the admissions process, welcoming prospective doctoral researchers while offering scientific programming for the broader community. As part of the 2026 symposium, Dr. Michael Muehlebach will deliver a keynote moderated by IMPRS-IS Scholar Ghadeer Elmkaiel. All MPI-IS members are warmly encouraged to join.
Dr. Michael Muehlebach – From Patterns to Interactions: What Dynamical Systems Tell Us About Learning Date: Wednesday, February 11, 2026 Time: 15:00 – 16:00 CET Location: Online (internal event)
My talk rethinks the foundations of machine learning by shifting from a largely static, statistical view of pattern recognition to a dynamical perspective: learning is an evolving process unfolding in time through continuous interaction with a surrounding environment. I will model core learning procedures, such as optimization, sampling, and robust training, as trajectories of dynamical systems, where notions such as reward, risk, resources, safety, and information gain can be treated as system-level design objectives and constraints.
I will illustrate how this viewpoint yields both conceptual clarity and concrete algorithmic benefits. We will derive min-max optimal rates for constrained optimization even when projections are replaced with surrogates that are computationally much cheaper to evaluate. The same dynamical template is extended to modern generative modeling, resulting in efficient sampling under nonconvex equality/inequality constraints via “landing”-type dynamics, and to robustness, where we frame adversarial training against label poisoning as a constrained optimization problem.
My talk will further highlight how fundamental research can unlock new application domains, from flow-based optimization in transportation networks, to energy-efficient passive soaring flight, and dynamical electromagnetic manipulation for medical microrobotics.
Michael Muehlebach studied mechanical engineering at ETH Zurich and specialized in robotics, systems, and control during his Master’s degree. He received the B.Sc. and the M.Sc. in 2010 and 2013, respectively, before joining the Institute for Dynamic Systems and Control for his Ph.D. He graduated under the supervision of Prof. R. D’Andrea in 2018 and joined the group of Prof. Michael I. Jordan at the University of California, Berkeley as a postdoctoral researcher. In 2021 he started as an independent group leader at the Max Planck Institute for Intelligent Systems in Tübingen, where he leads the group “Learning and Dynamical Systems.”
He is interested in a variety of subjects, including machine learning, dynamical systems, and optimization. During his Ph.D. he developed approximations to the constrained linear quadratic regulator problem, a central problem in control theory, and applied these to model predictive control. He also designed control and estimation algorithms for balancing robots and flying machines. His more recent work straddles the boundary between machine learning and optimization, and includes the analysis of momentum-based and constrained optimization algorithms from a dynamical systems point of view.
He received the Outstanding D-MAVT Bachelor Award for his Bachelor’s degree and the Willi-Studer Prize for the best Master’s degree. His Ph.D. thesis was awarded the ETH Medal and the HILTI Prize for innovative research. He was also awarded a Branco Weiss Fellowship, an Emmy Noether Fellowship, and an Amazon Research Grant, which fund his research group.
Access details for the keynote will be distributed via MPI-IS and IMPRS-IS community mailing lists. With questions about this event or how to join, please contact Sara Sorce (sara.sorce@tuebingen.mpg.de).
Please note: this is an internal event for MPI-IS and IMPRS-IS community members only.
More information